Optimizing Healthcare Analytics: A Zero-Inflated Poisson Approach toPediatric Emergency Room Visits

Title

Optimizing Healthcare Analytics: A Zero-Inflated Poisson Approach toPediatric Emergency Room Visits

Creator

Bose, Nadashree; Joshi, Hemlata

Description

In various fields, the modeling of count data holds significant importance. The Poisson regression model is a commonly utilized tool for this purpose. However, this model assumes that the data has uniform dispersion, a condition often not met in real-world observations. The nature of overdispersion canvary depending on the specific context. When the overdispersion is primarily dueto an excessive number of zero counts, the Zero-inflated Poisson regressionmodel becomes a more suitable choice for modeling count data. The paper commencesby offering a summary of the theoretical foundations of both Poisson regressionand Zero-inflated Poisson regression. To evaluate their performance, usethe Mean-Squared error (MSE) as a comparative metric. Next, apply these modelsto analyze the frequency of hospital emergency room visits by children between 1018 years of age. The overdispersion of the visit count in our dataset is mostly caused by the excessive occurrence of zero counts. The findings demonstratethat the Zero-inflated Poisson regression model outperforms the standard Poisson regression model in terms of MSE. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Source

Lecture Notes in Networks and Systems;Volume;1231 LNNS;pp.138-148

Date

01-01-2025

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

Count data; Emergency room visit; Excess of zeroes; Mean-Squared error; Poisson model; Zero-inflated Poisson model

Coverage

Bose N., Department of Statistics and Data Science, CHRIST (Deemed to be University), Bengaluru, India; Joshi H., Department of Statistics and Data Science, CHRIST (Deemed to be University), Bengaluru, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 23673370; ISBN: 978-303178945-8;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-3-031-78946-5_13

https://www.scopus.com/pages/publications/105007131783?origin=resultslist